论文信息 - Hybrid state space and echo state networks model of a miniature helicopter

Hybrid state space and echo state networks model of a miniature helicopter

To solve the problem of modeling the horizontal translational motion of a Raptor30 based miniature helicopter near hovering, a black-box model is built based on echo state networks. Combined with a state space angular motion model, a four-degree-of-freedom hybrid model is created. System identification is done using the remote control experiment data. Model validation results demonstrate that the model can predict the motion of the miniature helicopter near hovering on the whole. The model can be used to optimize parameterized controller. Closed-loop simulation further validates the model.

[1] Ben Tse,et al. Autonomous Inverted Helicopter Flight via Reinforcement Learning , 2004, ISER.

[2] Herbert Jaeger,et al. Adaptive Nonlinear System Identification with Echo State Networks , 2002, NIPS.

[3] Eric N. Johnson,et al. The Georgia Tech Unmanned Aerial Research Vehicle: GTMax , 2003 .

[4] S. Shankar Sastry,et al. Autonomous Helicopter Flight via Reinforcement Learning , 2003, NIPS.

[5] Lennart Ljung,et al. System Identification: Theory for the User , 1987 .

[6] Herbert Jaeger,et al. The''echo state''approach to analysing and training recurrent neural networks , 2001 .

[7] Munther A. Dahleh,et al. Avionics system for aggressive maneuvers , 2001 .

[8] Harald Haas,et al. Harnessing Nonlinearity: Predicting Chaotic Systems and Saving Energy in Wireless Communication , 2004, Science.

[9] Jia Pie-fa,et al. Research and Practice of a 30-class Autonomous Helicopter System , 2007 .

[10] Bernard Mettler. Modeling small-scale unmanned rotorcraft for advanced flight control design , 2001 .

[11] Herbert Jaeger,et al. Optimization and applications of echo state networks with leaky- integrator neurons , 2007, Neural Networks.

[12] Paul-Gerhard Plöger,et al. Echo State Networks used for Motor Control , 2005, Proceedings of the 2005 IEEE International Conference on Robotics and Automation.